© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105335
    Prev
    Next
    INDEX
    Explanations

    Alberta contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     These
    -2.97
     They
    -2.77
     этими
    -2.48
    h
    -2.45
    蕷
    -2.42
    躂
    -2.38
     contienen
    -2.34
    荸
    -2.33
     obstinate
    -2.31
     stuffy
    -2.30
    POSITIVE LOGITS
    which
    3.97
    緜
    3.06
    your
    2.92
    who
    2.89
    呖
    2.81
    婓
    2.78
    橚
    2.77
     proclaimed
    2.70
    驁
    2.70
    鹇
    2.69
    Activations Density 0.001%

    No Known Activations